function: image-processing
4273 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| mg-chao/snow-apps Snow Apps is a C++ open-source suite containing Snow Shot, a screenshot capture and annotation tool, and Snow Image Viewer. Snow Shot offer… | 67 | 4926 | active |
| wuyoscar/GPT-Image2-Skill A curated prompt gallery and library for OpenAI's GPT Image 2 model, packaged as an agentic skill and Python CLI for image generation and e… | 74 | 4923 | active |
| Augani/openreel-video OpenReel Video is a fully browser-based, open source video editor built with React, TypeScript, WebCodecs, and WebGPU. All editing and expo… | 77 | 4914 | active |
| eKoopmans/html2pdf.js html2pdf.js is a JavaScript library that converts webpages or DOM elements into printable PDF files entirely in the browser, built on html2… | 87 | 4913 | active |
| Chlumsky/msdfgen A C++ library and console tool that generates multi-channel signed distance fields (MSDFs) from vector shapes and font glyphs. The resultin… | 66 | 4912 | stable |
| googlefonts/noto-emoji Google's open-source Noto Emoji project providing Unicode-compliant emoji fonts, including a color emoji font (CBDT/CBLC format), a monochr… | 47 | 4904 | active |
| arrayfire/arrayfire ArrayFire is a general-purpose tensor/numerical computing library for C, C++, and Python that accelerates array operations on GPUs (CUDA, O… | 57 | 4902 | stable |
| KaiyangZhou/deep-person-reid Torchreid is a PyTorch library for deep-learning person re-identification, supporting both image and video reid with end-to-end training an… | 50 | 4900 | stable |
| mpetroff/pannellum Pannellum is a lightweight, free, open source panorama viewer for the web built with HTML5, CSS3, JavaScript, and WebGL. It ships as a sing… | 75 | 4881 | stable |
| tyxsspa/AnyText AnyText is the official implementation of a diffusion-based model for multilingual visual text generation and editing in images, accepted a… | 32 | 4874 | active |
| ZzzLc0405/photo-abstract-editorial A Codex Skill / prompt template that transforms a photo into a vertical editorial composition combining the original photo with an abstract… | 57 | 4868 | active |
| neilsonnn/image-blaster A Claude skillset that converts a single input image into a full 3D environment, including meshed 3D models (.glb/.obj), Gaussian splats (.… | 51 | 4822 | active |
| google/wuffs Wuffs is a memory-safe programming language plus a standard library for safely parsing, decoding and encoding untrusted file formats such a… | 75 | 4820 | active |
| lolcommits/lolcommits lolcommits is a Ruby CLI tool that automatically captures a webcam snapshot every time you make a git commit, archiving a lolcat-style self… | 78 | 4815 | active |
| aloshdenny/reverse-SynthID A research tool that reverse-engineers Google's SynthID watermark embedded in Gemini-generated images using spectral analysis and signal pr… | 66 | 4815 | active |
| endroid/qr-code A PHP library for generating QR codes with support for multiple writers (PNG, WebP, SVG, EPS, binary), logos, labels, and error correction.… | 62 | 4806 | stable |
| palxiao/poster-design XunPai Design (poster-design) is an open-source online image editor and poster designer built with Vue3, Vite, and Express, inspired by too… | 43 | 4802 | active |
| charmbracelet/freeze Freeze is a Go CLI tool that generates PNG, SVG, and WebP images of code snippets and terminal output. It supports syntax highlighting, ANS… | 71 | 4799 | active |
| UX-Decoder/Segment-Everything-Everywhere-All-At-Once SEEM is the official PyTorch implementation of the NeurIPS 2023 paper 'Segment Everything Everywhere All at Once', a model for universal im… | 20 | 4794 | stable |
| zju3dv/EasyMocap EasyMocap is an open-source Python toolbox for markerless human motion capture and novel view synthesis from RGB videos. It fits parametric… | 54 | 4783 | active |
| Bing-su/adetailer ADetailer is an extension for the Stable Diffusion WebUI (A1111) that automatically detects objects such as faces and hands in generated im… | 74 | 4781 | active |
| EFPrefix/EFQRCode EFQRCode is a lightweight, pure-Swift library for generating stylized QR code images (with watermarks, icons, or GIFs) and recognizing QR c… | 66 | 4755 | stable |
| cvg/LightGlue LightGlue is a deep neural network library that matches sparse local features across image pairs with high accuracy and fast inference. It … | 50 | 4728 | stable |
| esimov/pigo Pigo is a pure Go library for fast face detection, pupil/eye localization, and facial landmark detection based on the Pixel Intensity Compa… | 31 | 4728 | stable |
| CloudCompare/CloudCompare CloudCompare is a 3D point cloud and triangular mesh processing application, originally built to compare point clouds from laser scanners a… | 67 | 4693 | active |
| yangjian102621/geekai GeekAI is an open-source, self-hosted AI content creation platform integrating chat, image generation (MidJourney, DALL-E, Stable Diffusion… | 95 | 4686 | active |
| cf-pages/Telegraph-Image A free, self-deployable image hosting application that serves as a Flickr/Imgur alternative, built on Cloudflare Pages with uploads stored … | 75 | 4655 | active |
| f3d-app/f3d F3D is a fast, minimalist open-source 3D viewer desktop application supporting many formats (glTF, USD, STL, STEP, OBJ, FBX, Alembic) with … | 88 | 4650 | active |
| FooIbar/EhViewer A modern Android client for E-Hentai, overhauled with Material Design 3 and dynamic color support, forked from Ehviewer-Overhauled. It is a… | 86 | 4647 | active |
| Kwai-Kolors/Kolors Kolors is a large-scale latent diffusion model for photorealistic text-to-image synthesis, trained with bilingual (Chinese and English) tex… | 23 | 4615 | active |
| sensity-ai/dot dot (Deepfake Offensive Toolkit) is a Python tool that generates real-time, controllable deepfakes from a webcam feed and injects them into… | 23 | 4586 | active |
| joanrod/star-vector StarVector is a foundation model that generates scalable vector graphics (SVG) code from images and text by treating vectorization as a cod… | 49 | 4560 | active |
| xyxiao001/vue-cropper A Vue.js component plugin for cropping images in the browser, supporting Vue 2 and Vue 3. It offers rotation, zooming, fixed aspect ratios,… | 55 | 4559 | active |
| spipm/Depixelization_poc Depix is a proof-of-concept tool that recovers plaintext from pixelized screenshots by matching pixelated blocks against a rendered font se… | 10 | 4551 | active |
| crabbly/Print.js Print.js is a tiny JavaScript library that helps printing from the web, supporting printing of PDF, HTML, image, and JSON content directly … | 65 | 4545 | stable |
| TencentARC/InstantMesh InstantMesh is a feed-forward framework for generating 3D meshes from a single image using sparse-view large reconstruction models (LRM/Ins… | 25 | 4509 | active |
| mcmonkeyprojects/SwarmUI SwarmUI (formerly StableSwarmUI) is a modular, self-hosted web user interface for AI image generation, supporting models like Stable Diffus… | 76 | 4499 | active |
| burhanrashid52/PhotoEditor An Android photo editing library that lets apps add paint drawing, text, filters, emoji, and stickers to images, similar to Instagram/Faceb… | 73 | 4499 | stable |
| Aidoku/Aidoku Aidoku is a free, open-source manga reading application for iOS, iPadOS, and macOS with no ads. It supports local CBZ files, self-hosted me… | 92 | 4495 | active |
| royshil/obs-backgroundremoval An OBS Studio plugin that removes and replaces the background in portrait video using ONNX-based machine learning segmentation, acting as a… | 98 | 4492 | active |
| KnpLabs/snappy Snappy is a PHP library that wraps the wkhtmltopdf and wkhtmltoimage binaries to generate PDFs, snapshots, or thumbnails from URLs or HTML … | 92 | 4476 | stable |
| php-imagine/Imagine Imagine is an object-oriented image manipulation library for PHP, inspired by Python's PIL. It provides a unified API over GD2, Imagick, an… | 89 | 4471 | stable |
| cyanfish/naps2 NAPS2 is a free, open-source document scanning application for Windows, Mac, and Linux that supports WIA, TWAIN, SANE, and ESCL scanners an… | 97 | 4464 | active |
| astriaai/headshots-starter An open-source Next.js starter kit that generates professional AI headshots from user-uploaded selfies using Astria.ai's fine-tuning and in… | 40 | 4463 | active |
| metatube-community/jellyfin-plugin-metatube A metadata provider plugin for Jellyfin and Emby media servers that fetches movie and actor metadata from various internet providers via th… | 61 | 4454 | active |
| layumi/Person_reID_baseline_pytorch A small, friendly PyTorch baseline implementation for person and vehicle re-identification (ReID). It reproduces strong top-conference resu… | 65 | 4446 | stable |
| rom1504/img2dataset A Python tool that downloads large sets of image URLs and packages them into machine learning datasets, with resizing and caption support. … | 56 | 4443 | active |
| Zeejay0/gathered-scenes-zine-skill A collection of image-generation skills (prompt packs) written for Codex that transform ordinary photos into zine-style paper artworks. It … | 57 | 4440 | active |
| xlite-dev/lite.ai.toolkit A lightweight C++ toolkit providing unified APIs for 100+ pre-trained AI models across inference backends like ONNX Runtime, MNN, TensorRT,… | 74 | 4427 | active |
| Nutlope/restorePhotos A Next.js web application that restores old and blurry face photos using the GFPGAN ML model via the Replicate API. It provides a hosted se… | 31 | 4427 | active |
| huawei-noah/Efficient-AI-Backbones A collection of efficient neural network backbone architectures (GhostNet, TNT, ViG, WaveMLP, TinyNet, etc.) from Huawei Noah's Ark Lab, wi… | 28 | 4418 | active |
| codeforreal1/compressO CompressO is a free, open-source desktop app for compressing videos and images to tiny sizes entirely offline, built with Tauri, Rust, and … | 86 | 4415 | active |
| imazen/imageflow Imageflow is a high-performance, memory-safe image manipulation suite written in Rust, offering a C ABI library (libimageflow), a CLI tool … | 92 | 4412 | active |
| pyqtgraph/pyqtgraph PyQtGraph is a pure-Python graphics and GUI library built on PyQt/PySide and NumPy for fast 2D/3D scientific plotting and interactive data … | 73 | 4405 | stable |
| libjpeg-turbo/libjpeg-turbo libjpeg-turbo is a SIMD-accelerated JPEG image codec library that is API/ABI-compatible with libjpeg and generally 2-6x faster. It provides… | 88 | 4401 | stable |
| iperov/DeepFaceLab DeepFaceLab is the leading open-source Windows application for creating deepfakes, allowing users to swap, de-age, or replace faces and hea… | 10 | 19292 | maintenance |
| bowang-lab/MedSAM MedSAM is a fine-tuned Segment Anything Model (SAM) foundation model for universal medical image segmentation, trained on over 1.5 million … | 29 | 4379 | active |
| s1dashu/ip-as-logo-skill A compact Agent Skill that guides AI agents to generate highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos. It follows the… | 57 | 4374 | active |
| dreamgaussian/dreamgaussian DreamGaussian is the official PyTorch implementation of an ICLR 2024 Oral paper for efficient 3D content creation using generative Gaussian… | 18 | 4352 | active |
| VectorSpaceLab/OmniGen OmniGen is a unified diffusion-based image generation model that produces and edits images from multi-modal prompts without auxiliary modul… | 47 | 4340 | active |
| OHIF/Viewers OHIF Viewer is an open-source, zero-footprint web-based medical imaging viewer for DICOM images, built as a configurable and extensible pro… | 98 | 4309 | active |
| kohler/gifsicle Gifsicle is a command-line tool for creating, editing, and optimizing GIF images and animations, with companion programs gifview (a viewer)… | 62 | 4307 | stable |
| Baseflow/PhotoView PhotoView is an Android library providing a drop-in replacement for ImageView that supports zooming via multi-touch and double-tap gestures… | 23 | 18813 | maintenance |
| yuzutech/kroki Kroki is a unified HTTP API service that converts textual diagram descriptions (PlantUML, Mermaid, GraphViz, Ditaa, Excalidraw, and many mo… | 94 | 4297 | active |
| Tencent-Hunyuan/HunyuanDiT Hunyuan-DiT is Tencent's open-source diffusion transformer model for text-to-image generation with fine-grained Chinese language understand… | 49 | 4291 | active |
| richzhang/PerceptualSimilarity A PyTorch library implementing the LPIPS (Learned Perceptual Image Patch Similarity) metric, which measures perceptual distance between ima… | 23 | 4269 | stable |
| LycheeOrg/Lychee Lychee is a free, open-source, self-hosted photo management system with a web interface for uploading, organizing, and sharing photos. It r… | 95 | 4265 | active |
| hoothin/UserScripts A collection of Greasemonkey/Tampermonkey userscripts by hoothin, including Pagetual (auto-pager infinite scrolling), Picviewer CE+ (online… | 76 | 4264 | active |
| SysCV/sam-hq HQ-SAM (Segment Anything in High Quality) upgrades Meta's Segment Anything Model with a learnable High-Quality Output Token for accurate ze… | 48 | 4255 | active |
| ali-vilab/AnyDoor AnyDoor is the official implementation of a diffusion-based model that teleports target objects into new scenes at user-specified locations… | 28 | 4238 | active |
| TheAlphamerc/flutter_twitter_clone Fwitter is a fully functional Twitter clone mobile app built with the Flutter framework, using Firebase authentication, realtime database, … | 23 | 4237 | active |
| mausimus/ShaderGlass ShaderGlass is a Windows (and Wine) overlay application that applies GPU shader effects on top of the desktop, a window, or a captured sour… | 86 | 4214 | active |
| ArcReel/ArcReel ArcReel is an open-source, self-hosted AI video production workspace that turns novels, scripts, or product material into characters, scene… | 82 | 4211 | active |
| anthonynsimon/bild bild is a collection of parallel image processing algorithms written in pure Go, usable both as a Go library and as a CLI tool. It supports… | 96 | 4204 | active |
| TokisanGames/Terrain3D Terrain3D is a high-performance, editable terrain system for Godot 4, written in C++ as a GDExtension addon. It supports sculpting, texture… | 84 | 4199 | active |
| evanw/thumbhash ThumbHash is a compact encoding of an image placeholder that can be stored inline with data and rendered while the real image loads. It is … | 30 | 4197 | stable |
| cvg/Hierarchical-Localization hloc is a modular Python toolbox for state-of-the-art 6-DoF visual localization, combining image retrieval and feature matching (SuperPoint… | 48 | 4194 | active |
| oxipng/oxipng Oxipng is a multithreaded, lossless PNG/APNG compression optimizer written in Rust. It can be used as a command-line utility or as a Rust l… | 94 | 4188 | stable |
| fatihak/InkyPi InkyPi is an open-source E-Ink display application that runs on a Raspberry Pi and is controlled through a web interface. It supports plugi… | 66 | 4184 | active |
| lllyasviel/style2paints Style2Paints is an AI-driven tool that colorizes lineart sketches, optionally guided by human hints, style reference images, and lighting. … | 32 | 18179 | maintenance |
| hackerb9/lsix lsix is a shell script that displays image thumbnails directly in the terminal using sixel graphics, powered by ImageMagick. It works like … | 23 | 4174 | stable |
| Fannovel16/comfyui_controlnet_aux A collection of ComfyUI custom nodes providing ControlNet auxiliary preprocessors that generate hint images (Canny edges, lineart, depth ma… | 63 | 4163 | active |
| torchgeo/torchgeo TorchGeo is a PyTorch domain library, similar to torchvision, providing datasets, samplers, transforms, and pre-trained models specific to … | 95 | 4159 | active |
| bingoogolapple/BGABanner-Android An Android UI library providing banner/carousel components with swipe navigation for guide screens, infinite auto-looping for one or more p… | 75 | 4156 | active |
| nodeca/pica A browser-side JavaScript library for high-quality, high-speed image resizing using canvas, web workers, WebAssembly, and createImageBitmap… | 76 | 4144 | stable |
| RawTherapee/RawTherapee RawTherapee is a free, cross-platform raw photo processing program for developing images from digital cameras, written in C++ with a GTK fr… | 87 | 4134 | active |
| justadudewhohacks/face-api.js A JavaScript face detection and face recognition library built on top of tensorflow.js, usable in the browser and Node.js. It provides mode… | 23 | 17945 | maintenance |
| opengeos/segment-geospatial SamGeo (segment-geospatial) is a Python package that applies Meta AI's Segment Anything Model (SAM, SAM2, SAM3, HQ-SAM) to geospatial data … | 97 | 4122 | active |
| WebODM/WebODM WebODM is a user-friendly, commercial-grade application for drone image processing that generates georeferenced maps, point clouds, elevati… | 98 | 4116 | active |
| lllyasviel/sd-forge-layerdiffuse A Stable Diffusion WebUI (Forge) extension implementing Layer Diffusion to generate transparent images and separate foreground/background l… | 25 | 4116 | active |
| VectorSpaceLab/OmniGen2 OmniGen2 is an open-source unified multimodal generation model supporting text-to-image generation, instruction-guided image editing, and i… | 52 | 4112 | active |
| dominictobias/react-image-crop A dependency-free React component for responsive image cropping with pixel or percentage coordinates. It supports touch, keyboard accessibi… | 80 | 4103 | active |
| cdcseacave/openMVS OpenMVS is an open-source C++ library for Multi-View Stereo 3D reconstruction, taking camera poses and a sparse point-cloud as input and pr… | 76 | 4100 | active |
| ZhengPeng7/BiRefNet BiRefNet is a PyTorch implementation of the CAAI AIR 2024 paper 'Bilateral Reference for High-Resolution Dichotomous Image Segmentation'. I… | 65 | 4098 | active |
| twitter/twemoji Twemoji is a library from Twitter that provides standard Unicode emoji support across all platforms via a set of SVG/PNG assets and a JavaS… | 64 | 17763 | maintenance |
| GuyTevet/motion-diffusion-model Official PyTorch implementation of the Human Motion Diffusion Model (MDM) paper, generating 3D human motion sequences from text prompts usi… | 52 | 4092 | active |
| aFarkas/lazysizes lazysizes is a high-performance, SEO-friendly lazy loader for images (including responsive picture/srcset), iframes, scripts, and widgets. … | 23 | 17718 | maintenance |
| lllyasviel/Paints-UNDO Paints-UNDO is a family of deep learning models that take an image as input and generate the step-by-step drawing sequence (sketching, inki… | 40 | 4067 | active |
| Dimezis/BlurView An Android library providing a BlurView, a FrameLayout-like view that dynamically blurs its underlying content in an iOS-like fashion and r… | 77 | 4045 | active |
| armory3d/armorpaint ArmorPaint is a stand-alone 3D PBR texture painting application that runs entirely on the GPU, supporting node-based procedural materials, … | 67 | 4039 | active |